Find centralized, trusted content and collaborate around the technologies you use most.
Teams
Q&A for work
Connect and share knowledge within a single location that is structured and easy to search.
当使用 TF 的 Conv2D 层时padding='SAME'，即期望输出与输入具有相同的 2D 形状时，它是先用零填充输入然后进行卷积，还是首先按原样计算输入上的卷积，然后对结果应用零填充？
padding='SAME'